© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 31037
    Prev
    Next
    INDEX
    Explanations

    copyright authors and licencing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    skins
    -0.08
    æľīåħ³äºĭ项
    -0.08
     rog
    -0.08
    éĢłåĮĸ
    -0.07
    顾åIJįæĢĿ
    -0.07
    skin
    -0.07
    egan
    -0.07
    éĴīéĴī
    -0.07
    ä»»æĢ¨
    -0.07
    ::$
    -0.07
    POSITIVE LOGITS
    é½
    0.07
    ä¸įå¿ĺ
    0.07
    etch
    0.07
    ewe
    0.06
    izards
    0.06
     enlisted
    0.06
    游走
    0.06
    èµ°
    0.06
     confl
    0.06
    utherland
    0.06
    Activations Density 0.020%

    No Known Activations